Implementation notes: amd64, glyme, crypto_aead/hs1sivhiv2

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: hs1sivhiv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
22352	`faster`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
22352	`faster`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
23328	`faster`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
23440	`faster`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
23528	`faster`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
23660	`faster`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
23660	`faster`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
23684	`faster`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
23796	`faster`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
23948	`faster`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
23972	`faster`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
23972	`faster`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
23972	`faster`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
24116	`faster`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
24120	`faster`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
24124	`faster`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
24128	`faster`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
24592	`faster`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
24640	`dolbeau/amd64-sse`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
24640	`dolbeau/amd64-sse`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
25424	`faster`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
25432	`faster`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
25432	`faster`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
25440	`faster`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
25444	`faster`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
25656	`faster`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
25656	`faster`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
25684	`faster`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
25752	`faster`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
25760	`faster`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
25800	`faster`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
25820	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
25864	`faster`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
25876	`faster`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
25896	`faster`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
25912	`faster`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
25940	`faster`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
25948	`faster`	`gcc -O3 -fomit-frame-pointer`	20170204	20170105
25948	`faster`	`gcc -m64 -O3 -fomit-frame-pointer`	20170204	20170105
25968	`faster`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
26008	`faster`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
26016	`faster`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170204	20170105
26028	`faster`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170204	20170105
26120	`faster`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
26136	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
26136	`faster`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
26140	`faster`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
26200	`faster`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
26208	`faster`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
26208	`faster`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
26212	`faster`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
26220	`faster`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
26320	`faster`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170204	20170105
26320	`faster`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
26336	`faster`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
26336	`faster`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
26388	`faster`	`gcc -O2 -fomit-frame-pointer`	20170204	20170105
26388	`faster`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
26388	`faster`	`gcc -m64 -O2 -fomit-frame-pointer`	20170204	20170105
26408	`faster`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
26432	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
26440	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
26452	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
26472	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
26476	`faster`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170204	20170105
26476	`faster`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
26488	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
26492	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
26496	`faster`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
26496	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
26508	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
26508	`faster`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
26516	`faster`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
26524	`faster`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
26532	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
26600	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
26600	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
26624	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
26756	`faster`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
27212	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
27232	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
27244	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
27280	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
27284	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
27284	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
27344	`faster`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
27344	`faster`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
27612	`faster`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
27636	`faster`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
27636	`faster`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
27660	`faster`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
27700	`faster`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
27720	`faster`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
27784	`faster`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
27796	`faster`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
27796	`faster`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170204	20170105
27820	`faster`	`gcc -m64 -Os -fomit-frame-pointer`	20170204	20170105
27828	`faster`	`gcc -Os -fomit-frame-pointer`	20170204	20170105
27848	`faster`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170204	20170105
27912	`faster`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
27924	`faster`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
27944	`faster`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170204	20170105
27952	`faster`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
27952	`faster`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
27972	`faster`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
28016	`faster`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170204	20170105
28016	`faster`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
28036	`faster`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170204	20170105
28080	`faster`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
28100	`faster`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
28104	`faster`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
28104	`faster`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170204	20170105
28128	`faster`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
28208	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
28360	`faster`	`gcc -march=k8 -O -fomit-frame-pointer`	20170204	20170105
28368	`faster`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
28388	`faster`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
28392	`faster`	`gcc -march=nocona -O -fomit-frame-pointer`	20170204	20170105
28612	`faster`	`gcc -O -fomit-frame-pointer`	20170204	20170105
28620	`faster`	`gcc -m64 -O -fomit-frame-pointer`	20170204	20170105
28656	`faster`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
32584	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
32584	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
32600	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
32888	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
32892	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
33608	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
56204	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
56232	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
57012	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
57016	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
57060	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
57068	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
57080	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
57152	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
57344	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
57356	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170204	20170105
57356	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170204	20170105
57392	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
57400	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
57808	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
57968	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
59168	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170204	20170105
59176	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
59208	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170204	20170105
59468	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
59492	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
59532	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
59532	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
60016	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
60076	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
60280	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
60284	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
60300	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
60344	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
60556	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
60600	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
60616	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
61264	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
63884	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
63956	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
64008	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
64040	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
64160	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
64176	`ref`	`gcc -O3 -fomit-frame-pointer`	20170204	20170105
64444	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20170204	20170105
77512	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
77512	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
77736	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
77744	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
78364	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
78376	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170204	20170105
78652	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
78680	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
79532	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
79540	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
79804	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
79884	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170204	20170105
79896	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170204	20170105
80676	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
80688	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
81184	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
81188	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
81200	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
81236	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
82804	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
82820	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170204	20170105
83372	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
83440	`ref`	`gcc -O2 -fomit-frame-pointer`	20170204	20170105
83456	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20170204	20170105
91888	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
91892	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
91892	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
91932	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
92384	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
92460	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
92780	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20170204	20170105
93028	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
93036	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
93064	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
93388	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
93412	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
93436	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
93444	`ref`	`gcc -Os -fomit-frame-pointer`	20170204	20170105
93452	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
93460	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20170204	20170105
93464	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
94156	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170204	20170105
94184	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170204	20170105
94216	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
94220	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
94220	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
94224	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
94272	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
94336	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
94500	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
94920	`ref`	`gcc -O -fomit-frame-pointer`	20170204	20170105
95124	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20170204	20170105
95148	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
95192	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
95288	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
95324	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
95324	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
95364	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
95368	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
98292	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20170204	20170105
98352	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
98564	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
98648	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
100988	`faster`	`cc`	20170204	20170105
122084	`faster`	`gcc -funroll-loops`	20170204	20170105
122412	`faster`	`gcc`	20170204	20170105
632328	`ref`	`gcc -funroll-loops`	20170204	20170105
633708	`ref`	`gcc`	20170204	20170105
695848	`ref`	`cc`	20170204	20170105

Test failure

Implementation: crypto_aead/hs1sivhiv2/faster
Compiler: gcc -fno-schedule-insns -O3 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	faster

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-sse
Compiler: cc

encrypt.c: In file included from encrypt.c:192:
encrypt.c: ./c256.h:98:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor368' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 0, 4, 8,12);
encrypt.c: ^
encrypt.c: ./c256.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c256.h:12:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ^
encrypt.c: ./c256.h:98:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor368' that is compiled without support for 'ssse3'
encrypt.c: ./c256.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c256.h:14:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ^
encrypt.c: ./c256.h:99:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor368' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 1, 5, 9,13);
encrypt.c: ^
encrypt.c: ./c256.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c256.h:12:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
cc	dolbeau/amd64-sse
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx2
Compiler: cc

encrypt.c: encrypt.c:90:2: error: "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^
encrypt.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 7, namely:

Compiler	Implementations
cc	dolbeau/amd64-avx2
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx2
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx512
Compiler: cc

encrypt.c: encrypt.c:90:2: error: "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^
encrypt.c: encrypt.c:342:15: error: invalid input constraint 'Yz' in asm
encrypt.c: : [a] "Yz" (a)
encrypt.c: ^
encrypt.c: encrypt.c:505:26: warning: implicit declaration of function '_mm512_loadu_si512' is invalid in C99 [-Wimplicit-function-declaration]
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^
encrypt.c: encrypt.c:505:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:506:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv4 = _mm512_loadu_si512((const __m512i*)(nhkey+ 4)); // 1
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:507:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv8 = _mm512_loadu_si512((const __m512i*)(nhkey+ 8)); // 1, 2
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:508:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv12 = _mm512_loadu_si512((const __m512i*)(nhkey+12)); // 1, 2
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:509:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv16 = _mm512_loadu_si512((const __m512i*)(nhkey+16)); // 2, 3
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:510:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 7, namely:

Compiler	Implementations
cc	dolbeau/amd64-avx512
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx512
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx512
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-sse
Compiler: gcc

Number of similar (compiler,implementation) pairs: 70, namely:

Compiler	Implementations
gcc	dolbeau/amd64-sse
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops	dolbeau/amd64-sse
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx2
Compiler: gcc

Number of similar (compiler,implementation) pairs: 93, namely:

Compiler	Implementations
gcc	dolbeau/amd64-avx2
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops	dolbeau/amd64-avx2
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx512
Compiler: gcc

Number of similar (compiler,implementation) pairs: 94, namely:

Compiler	Implementations
gcc	dolbeau/amd64-avx512
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops	dolbeau/amd64-avx512
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx2
Compiler: gcc -funroll-loops -m64 -O2 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^~~~~
encrypt.c: encrypt.c: In function 'chacha_noxor32':
encrypt.c: encrypt.c:214:17: fatal error: c32.h: No such file or directory
encrypt.c: #include "c32.h"
encrypt.c: ^
encrypt.c: compilation terminated.

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-sse
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c256.h: In function 'chacha_noxor368':
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:14:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c256.h:17:36: note: in expansion of macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c256.h:105:7: note: in expansion of macro 'VEC4_QUARTERROUND'
encrypt.c: VEC4_QUARTERROUND( 3, 4, 9,14);
encrypt.c: ^~~~~~~~~~~~~~~~~
encrypt.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:12:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: ...
encrypt.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c256.h: In function 'chacha_noxor368':
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:14:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c256.h:17:36: note: in expansion of macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c256.h:105:7: note: in expansion of macro 'VEC4_QUARTERROUND'
encrypt.c: VEC4_QUARTERROUND( 3, 4, 9,14);
encrypt.c: ^~~~~~~~~~~~~~~~~
encrypt.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:12:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx2
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^~~~~
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:110:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i rot16 = _mm256_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2,13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
encrypt.c: ^~~~~
encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^~~~~
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:110:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i rot16 = _mm256_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2,13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
encrypt.c: ^~~~~

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx512
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^~~~~
encrypt.c: encrypt.c: In function '_mm512_reduce_add_epi64':
encrypt.c: encrypt.c:329:20: note: The ABI for passing parameters with 64-byte alignment has changed in GCC 4.6
encrypt.c: unsigned long long _mm512_reduce_add_epi64 (__m512i a) {
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:110:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i rot16 = _mm256_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2,13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
encrypt.c: ^~~~~
encrypt.c: encrypt.c: In function 'prf_hash2_3':
encrypt.c: encrypt.c:505:19: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^~~
encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^~~~~
encrypt.c: encrypt.c: In function '_mm512_reduce_add_epi64':
encrypt.c: encrypt.c:329:20: note: The ABI for passing parameters with 64-byte alignment has changed in GCC 4.6
encrypt.c: unsigned long long _mm512_reduce_add_epi64 (__m512i a) {
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:110:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i rot16 = _mm256_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2,13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
encrypt.c: ^~~~~
encrypt.c: encrypt.c: In function 'prf_hash2_3':
encrypt.c: encrypt.c:505:19: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^~~

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512